mirror of
https://github.com/MariaDB/server.git
synced 2025-02-15 18:05:32 +01:00
ad0d203f2e
The problem occurs in parallel replication in GTID mode, when we are using multiple replication domains. In this case, if the SQL thread stops, the slave GTID position may refer to a different point in the relay log for each domain. The bug was that when the SQL thread was stopped and restarted (but the IO thread was kept running), the SQL thread would resume applying the relay log from the point of the most advanced replication domain, silently skipping all earlier events within other domains. This caused replication corruption. This patch solves the problem by storing, when the SQL thread stops with multiple parallel replication domains active, the current GTID position. Additionally, the current position in the relay logs is moved back to a point known to be earlier than the current position of any replication domain. Then when the SQL thread restarts from the earlier position, GTIDs encountered are compared against the stored GTID position. Any GTID that was already applied before the stop is skipped to avoid duplicate apply. This patch should have no effect if multi-domain GTID parallel replication is not used. Similarly, if both SQL and IO thread are stopped and restarted, the patch has no effect, as in this case the existing relay logs are removed and re-fetched from the master at the current global @@gtid_slave_pos.
132 lines
3.2 KiB
Text
132 lines
3.2 KiB
Text
--source include/have_innodb.inc
|
|
--source include/have_debug.inc
|
|
--source include/have_debug_sync.inc
|
|
--source include/master-slave.inc
|
|
|
|
--connection server_2
|
|
SET @old_parallel_threads=@@GLOBAL.slave_parallel_threads;
|
|
--source include/stop_slave.inc
|
|
SET GLOBAL slave_parallel_threads=10;
|
|
CHANGE MASTER TO master_use_gtid=current_pos;
|
|
--source include/start_slave.inc
|
|
|
|
|
|
--echo *** MDEV-6589: Incorrect relay log start position when restarting SQL thread after error in parallel replication ***
|
|
|
|
--connection server_1
|
|
ALTER TABLE mysql.gtid_slave_pos ENGINE=InnoDB;
|
|
CREATE TABLE t1 (a int PRIMARY KEY) ENGINE=MyISAM;
|
|
CREATE TABLE t2 (a int PRIMARY KEY) ENGINE=InnoDB;
|
|
INSERT INTO t1 VALUES (1);
|
|
INSERT INTO t2 VALUES (1);
|
|
--save_master_pos
|
|
|
|
--connection server_2
|
|
--sync_with_master
|
|
SELECT * FROM t1;
|
|
SELECT * FROM t2;
|
|
|
|
# Block one domain, which we will later cause to give an error. And let some
|
|
# other domains proceed so we can check that after restart, the slave is able
|
|
# to correctly restart each domain in a separate position.
|
|
|
|
--connect (con_temp1,127.0.0.1,root,,test,$SERVER_MYPORT_2,)
|
|
SET sql_log_bin=0;
|
|
BEGIN;
|
|
INSERT INTO t2 VALUES (5);
|
|
|
|
--connection server_1
|
|
SET gtid_domain_id=0;
|
|
INSERT INTO t1 VALUES (2);
|
|
INSERT INTO t2 VALUES (3);
|
|
FLUSH LOGS;
|
|
INSERT INTO t1 VALUES (4);
|
|
|
|
SET gtid_domain_id=1;
|
|
# This query will be blocked on the slave, and later give a duplicate key error.
|
|
INSERT INTO t2 VALUES (5);
|
|
|
|
SET gtid_domain_id=0;
|
|
INSERT INTO t1 VALUES (6);
|
|
INSERT INTO t1 VALUES (7);
|
|
|
|
SET gtid_domain_id=2;
|
|
INSERT INTO t2 VALUES (8);
|
|
INSERT INTO t1 VALUES (9);
|
|
FLUSH LOGS;
|
|
|
|
SET gtid_domain_id=3;
|
|
INSERT INTO t2 VALUES (10);
|
|
INSERT INTO t1 VALUES (11);
|
|
|
|
# These cannot be replicated before the error, as a prior commit is blocked.
|
|
SET gtid_domain_id=1;
|
|
INSERT INTO t1 VALUES (12);
|
|
INSERT INTO t2 VALUES (13);
|
|
|
|
SET gtid_domain_id=0;
|
|
INSERT INTO t2 VALUES (14);
|
|
FLUSH LOGS;
|
|
|
|
SET gtid_domain_id=3;
|
|
INSERT INTO t2 VALUES (15);
|
|
|
|
SET gtid_domain_id=2;
|
|
INSERT INTO t2 VALUES (16);
|
|
|
|
SET gtid_domain_id=0;
|
|
INSERT INTO t1 VALUES (17);
|
|
SET @gtid0 = @@last_gtid;
|
|
SET gtid_domain_id=2;
|
|
INSERT INTO t1 VALUES (18);
|
|
SET @gtid2 = @@last_gtid;
|
|
SET gtid_domain_id=3;
|
|
INSERT INTO t1 VALUES (19);
|
|
SET @gtid3 = @@last_gtid;
|
|
--let $wait_pos= `SELECT CONCAT(@gtid0, ",", @gtid2, ",", @gtid3)`
|
|
|
|
SELECT * FROM t1 ORDER BY a;
|
|
SELECT * FROM t2 ORDER BY a;
|
|
--source include/save_master_gtid.inc
|
|
|
|
|
|
--connection server_2
|
|
# First wait for domains 0, 2, and 3 to complete.
|
|
--replace_result $wait_pos WAIT_POS
|
|
eval SELECT MASTER_GTID_WAIT('$wait_pos');
|
|
|
|
# Then release the row lock, and wait for the domain 1 to fail with
|
|
# duplicate key error.
|
|
--connection con_temp1
|
|
COMMIT;
|
|
SET sql_log_bin=1;
|
|
|
|
--connection server_2
|
|
--let $slave_sql_errno= 1062
|
|
--source include/wait_for_slave_sql_error.inc
|
|
|
|
SELECT * FROM t1 ORDER BY a;
|
|
SELECT * FROM t2 ORDER BY a;
|
|
|
|
SET sql_log_bin=0;
|
|
DELETE FROM t2 WHERE a=5;
|
|
SET sql_log_bin=1;
|
|
--source include/start_slave.inc
|
|
--source include/sync_with_master_gtid.inc
|
|
|
|
SELECT * FROM t1 ORDER BY a;
|
|
SELECT * FROM t2 ORDER BY a;
|
|
|
|
|
|
# Clean up.
|
|
--connection server_2
|
|
--source include/stop_slave.inc
|
|
SET GLOBAL slave_parallel_threads=@old_parallel_threads;
|
|
--source include/start_slave.inc
|
|
SET DEBUG_SYNC= 'RESET';
|
|
|
|
--connection server_1
|
|
DROP TABLE t1,t2;
|
|
SET DEBUG_SYNC= 'RESET';
|
|
|
|
--source include/rpl_end.inc
|